https://github.com/fhahn created https://github.com/llvm/llvm-project/pull/135666
Back-porting properly freezing of the start value during epilogue vectorization (https://github.com/llvm/llvm-project/commit/2bdc1a1337692a5743658ba6b680e5d914e684a4) is non-trivial. For the 20.x release, just disable epilogue vectorization for FindLastIV reductions where the start value may be poison or undef. Fixes https://github.com/llvm/llvm-project/issues/126836. >From e21b3211d2129e3e0110bcaa75ab0b451397ef42 Mon Sep 17 00:00:00 2001 From: Florian Hahn <f...@fhahn.com> Date: Mon, 14 Apr 2025 17:16:08 +0100 Subject: [PATCH 1/2] [LV] Add tests with FindLastIV and epilogue vectorization. Tests for #126836. --- .../AArch64/epilog-iv-select-cmp.ll | 250 ++++++++++++++++++ .../LoopVectorize/epilog-iv-select-cmp.ll | 127 ++++++++- 2 files changed, 366 insertions(+), 11 deletions(-) create mode 100644 llvm/test/Transforms/LoopVectorize/AArch64/epilog-iv-select-cmp.ll diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/epilog-iv-select-cmp.ll b/llvm/test/Transforms/LoopVectorize/AArch64/epilog-iv-select-cmp.ll new file mode 100644 index 0000000000000..b2643aa11d1fd --- /dev/null +++ b/llvm/test/Transforms/LoopVectorize/AArch64/epilog-iv-select-cmp.ll @@ -0,0 +1,250 @@ +; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --version 5 +; RUN: opt -passes=loop-vectorize -mtriple=arm64-apple-macosx -S %s | FileCheck %s + +define i8 @select_icmp_var_start(ptr %a, i8 %n, i8 %start) { +; CHECK-LABEL: define i8 @select_icmp_var_start( +; CHECK-SAME: ptr [[A:%.*]], i8 [[N:%.*]], i8 [[START:%.*]]) { +; CHECK-NEXT: [[ITER_CHECK:.*]]: +; CHECK-NEXT: [[TMP0:%.*]] = add i8 [[N]], -1 +; CHECK-NEXT: [[TMP1:%.*]] = zext i8 [[TMP0]] to i32 +; CHECK-NEXT: [[TMP2:%.*]] = add nuw nsw i32 [[TMP1]], 1 +; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[TMP2]], 8 +; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label %[[VEC_EPILOG_SCALAR_PH:.*]], label %[[VECTOR_MAIN_LOOP_ITER_CHECK:.*]] +; CHECK: [[VECTOR_MAIN_LOOP_ITER_CHECK]]: +; CHECK-NEXT: [[MIN_ITERS_CHECK1:%.*]] = icmp ult i32 [[TMP2]], 32 +; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK1]], label %[[VEC_EPILOG_PH:.*]], label %[[VECTOR_PH:.*]] +; CHECK: [[VECTOR_PH]]: +; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i32 [[TMP2]], 32 +; CHECK-NEXT: [[N_VEC:%.*]] = sub i32 [[TMP2]], [[N_MOD_VF]] +; CHECK-NEXT: [[TMP3:%.*]] = trunc i32 [[N_VEC]] to i8 +; CHECK-NEXT: br label %[[VECTOR_BODY:.*]] +; CHECK: [[VECTOR_BODY]]: +; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_IND:%.*]] = phi <16 x i8> [ <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <16 x i8> [ splat (i8 -128), %[[VECTOR_PH]] ], [ [[TMP10:%.*]], %[[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI2:%.*]] = phi <16 x i8> [ splat (i8 -128), %[[VECTOR_PH]] ], [ [[TMP11:%.*]], %[[VECTOR_BODY]] ] +; CHECK-NEXT: [[STEP_ADD:%.*]] = add <16 x i8> [[VEC_IND]], splat (i8 16) +; CHECK-NEXT: [[INDEX4:%.*]] = trunc i32 [[INDEX]] to i8 +; CHECK-NEXT: [[TMP5:%.*]] = add i8 [[INDEX4]], 0 +; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i8, ptr [[A]], i8 [[TMP5]] +; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds i8, ptr [[TMP8]], i32 0 +; CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds i8, ptr [[TMP8]], i32 16 +; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <16 x i8>, ptr [[TMP9]], align 8 +; CHECK-NEXT: [[WIDE_LOAD3:%.*]] = load <16 x i8>, ptr [[TMP7]], align 8 +; CHECK-NEXT: [[TMP17:%.*]] = icmp eq <16 x i8> [[WIDE_LOAD]], splat (i8 3) +; CHECK-NEXT: [[TMP23:%.*]] = icmp eq <16 x i8> [[WIDE_LOAD3]], splat (i8 3) +; CHECK-NEXT: [[TMP10]] = select <16 x i1> [[TMP17]], <16 x i8> [[VEC_IND]], <16 x i8> [[VEC_PHI]] +; CHECK-NEXT: [[TMP11]] = select <16 x i1> [[TMP23]], <16 x i8> [[STEP_ADD]], <16 x i8> [[VEC_PHI2]] +; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 32 +; CHECK-NEXT: [[VEC_IND_NEXT]] = add <16 x i8> [[STEP_ADD]], splat (i8 16) +; CHECK-NEXT: [[TMP12:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]] +; CHECK-NEXT: br i1 [[TMP12]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]] +; CHECK: [[MIDDLE_BLOCK]]: +; CHECK-NEXT: [[RDX_MINMAX:%.*]] = call <16 x i8> @llvm.smax.v16i8(<16 x i8> [[TMP10]], <16 x i8> [[TMP11]]) +; CHECK-NEXT: [[TMP13:%.*]] = call i8 @llvm.vector.reduce.smax.v16i8(<16 x i8> [[RDX_MINMAX]]) +; CHECK-NEXT: [[RDX_SELECT_CMP12:%.*]] = icmp ne i8 [[TMP13]], -128 +; CHECK-NEXT: [[RDX_SELECT:%.*]] = select i1 [[RDX_SELECT_CMP12]], i8 [[TMP13]], i8 [[START]] +; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i32 [[TMP2]], [[N_VEC]] +; CHECK-NEXT: br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[VEC_EPILOG_ITER_CHECK:.*]] +; CHECK: [[VEC_EPILOG_ITER_CHECK]]: +; CHECK-NEXT: [[IND_END:%.*]] = trunc i32 [[N_VEC]] to i8 +; CHECK-NEXT: [[N_VEC_REMAINING:%.*]] = sub i32 [[TMP2]], [[N_VEC]] +; CHECK-NEXT: [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i32 [[N_VEC_REMAINING]], 8 +; CHECK-NEXT: br i1 [[MIN_EPILOG_ITERS_CHECK]], label %[[VEC_EPILOG_SCALAR_PH]], label %[[VEC_EPILOG_PH]] +; CHECK: [[VEC_EPILOG_PH]]: +; CHECK-NEXT: [[VEC_EPILOG_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], %[[VEC_EPILOG_ITER_CHECK]] ], [ 0, %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ] +; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i8 [ [[TMP3]], %[[VEC_EPILOG_ITER_CHECK]] ], [ 0, %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ] +; CHECK-NEXT: [[BC_MERGE_RDX:%.*]] = phi i8 [ [[RDX_SELECT]], %[[VEC_EPILOG_ITER_CHECK]] ], [ [[START]], %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ] +; CHECK-NEXT: [[TMP14:%.*]] = icmp eq i8 [[BC_MERGE_RDX]], [[START]] +; CHECK-NEXT: [[TMP15:%.*]] = select i1 [[TMP14]], i8 -128, i8 [[BC_MERGE_RDX]] +; CHECK-NEXT: [[N_MOD_VF4:%.*]] = urem i32 [[TMP2]], 8 +; CHECK-NEXT: [[N_VEC5:%.*]] = sub i32 [[TMP2]], [[N_MOD_VF4]] +; CHECK-NEXT: [[TMP16:%.*]] = trunc i32 [[N_VEC5]] to i8 +; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <8 x i8> poison, i8 [[BC_RESUME_VAL]], i64 0 +; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <8 x i8> [[DOTSPLATINSERT]], <8 x i8> poison, <8 x i32> zeroinitializer +; CHECK-NEXT: [[INDUCTION:%.*]] = add <8 x i8> [[DOTSPLAT]], <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7> +; CHECK-NEXT: [[DOTSPLATINSERT10:%.*]] = insertelement <8 x i8> poison, i8 [[TMP15]], i64 0 +; CHECK-NEXT: [[DOTSPLAT11:%.*]] = shufflevector <8 x i8> [[DOTSPLATINSERT10]], <8 x i8> poison, <8 x i32> zeroinitializer +; CHECK-NEXT: br label %[[VEC_EPILOG_VECTOR_BODY:.*]] +; CHECK: [[VEC_EPILOG_VECTOR_BODY]]: +; CHECK-NEXT: [[INDEX6:%.*]] = phi i32 [ [[VEC_EPILOG_RESUME_VAL]], %[[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT13:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_IND7:%.*]] = phi <8 x i8> [ [[INDUCTION]], %[[VEC_EPILOG_PH]] ], [ [[VEC_IND_NEXT8:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI9:%.*]] = phi <8 x i8> [ [[DOTSPLAT11]], %[[VEC_EPILOG_PH]] ], [ [[TMP20:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ] +; CHECK-NEXT: [[IV:%.*]] = trunc i32 [[INDEX6]] to i8 +; CHECK-NEXT: [[TMP24:%.*]] = add i8 [[IV]], 0 +; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds i8, ptr [[A]], i8 [[TMP24]] +; CHECK-NEXT: [[TMP18:%.*]] = getelementptr inbounds i8, ptr [[GEP]], i32 0 +; CHECK-NEXT: [[WIDE_LOAD12:%.*]] = load <8 x i8>, ptr [[TMP18]], align 8 +; CHECK-NEXT: [[TMP19:%.*]] = icmp eq <8 x i8> [[WIDE_LOAD12]], splat (i8 3) +; CHECK-NEXT: [[TMP20]] = select <8 x i1> [[TMP19]], <8 x i8> [[VEC_IND7]], <8 x i8> [[VEC_PHI9]] +; CHECK-NEXT: [[INDEX_NEXT13]] = add nuw i32 [[INDEX6]], 8 +; CHECK-NEXT: [[VEC_IND_NEXT8]] = add <8 x i8> [[VEC_IND7]], splat (i8 8) +; CHECK-NEXT: [[TMP21:%.*]] = icmp eq i32 [[INDEX_NEXT13]], [[N_VEC5]] +; CHECK-NEXT: br i1 [[TMP21]], label %[[VEC_EPILOG_MIDDLE_BLOCK:.*]], label %[[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]] +; CHECK: [[VEC_EPILOG_MIDDLE_BLOCK]]: +; CHECK-NEXT: [[TMP22:%.*]] = call i8 @llvm.vector.reduce.smax.v8i8(<8 x i8> [[TMP20]]) +; CHECK-NEXT: [[RDX_SELECT_CMP14:%.*]] = icmp ne i8 [[TMP22]], -128 +; CHECK-NEXT: [[RDX_SELECT15:%.*]] = select i1 [[RDX_SELECT_CMP14]], i8 [[TMP22]], i8 [[START]] +; CHECK-NEXT: [[CMP_N16:%.*]] = icmp eq i32 [[TMP2]], [[N_VEC5]] +; CHECK-NEXT: br i1 [[CMP_N16]], label %[[EXIT]], label %[[VEC_EPILOG_SCALAR_PH]] +; CHECK: [[VEC_EPILOG_SCALAR_PH]]: +; CHECK-NEXT: [[BC_RESUME_VAL17:%.*]] = phi i8 [ [[TMP16]], %[[VEC_EPILOG_MIDDLE_BLOCK]] ], [ 0, %[[ITER_CHECK]] ], [ [[IND_END]], %[[VEC_EPILOG_ITER_CHECK]] ] +; CHECK-NEXT: [[BC_MERGE_RDX18:%.*]] = phi i8 [ [[RDX_SELECT15]], %[[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[START]], %[[ITER_CHECK]] ], [ [[RDX_SELECT]], %[[VEC_EPILOG_ITER_CHECK]] ] +; CHECK-NEXT: br label %[[LOOP:.*]] +; CHECK: [[LOOP]]: +; CHECK-NEXT: [[IV1:%.*]] = phi i8 [ [[BC_RESUME_VAL17]], %[[VEC_EPILOG_SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ] +; CHECK-NEXT: [[RDX:%.*]] = phi i8 [ [[BC_MERGE_RDX18]], %[[VEC_EPILOG_SCALAR_PH]] ], [ [[SEL:%.*]], %[[LOOP]] ] +; CHECK-NEXT: [[GEP1:%.*]] = getelementptr inbounds i8, ptr [[A]], i8 [[IV1]] +; CHECK-NEXT: [[L:%.*]] = load i8, ptr [[GEP1]], align 8 +; CHECK-NEXT: [[C:%.*]] = icmp eq i8 [[L]], 3 +; CHECK-NEXT: [[SEL]] = select i1 [[C]], i8 [[IV1]], i8 [[RDX]] +; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i8 [[IV1]], 1 +; CHECK-NEXT: [[EC:%.*]] = icmp eq i8 [[IV_NEXT]], [[N]] +; CHECK-NEXT: br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP4:![0-9]+]] +; CHECK: [[EXIT]]: +; CHECK-NEXT: [[SEL_LCSSA:%.*]] = phi i8 [ [[SEL]], %[[LOOP]] ], [ [[RDX_SELECT]], %[[MIDDLE_BLOCK]] ], [ [[RDX_SELECT15]], %[[VEC_EPILOG_MIDDLE_BLOCK]] ] +; CHECK-NEXT: ret i8 [[SEL_LCSSA]] +; +entry: + br label %loop + +loop: + %iv = phi i8 [ 0, %entry ], [ %iv.next, %loop ] + %rdx = phi i8 [ %start, %entry ], [ %sel, %loop ] + %gep = getelementptr inbounds i8, ptr %a, i8 %iv + %l = load i8, ptr %gep, align 8 + %c = icmp eq i8 %l, 3 + %sel = select i1 %c, i8 %iv, i8 %rdx + %iv.next = add nuw nsw i8 %iv, 1 + %ec = icmp eq i8 %iv.next, %n + br i1 %ec, label %exit, label %loop + +exit: + ret i8 %sel +} + +define i32 @select_icmp_var_start_iv_trunc(i32 %N, i32 %start) #0 { +; CHECK-LABEL: define i32 @select_icmp_var_start_iv_trunc( +; CHECK-SAME: i32 [[N:%.*]], i32 [[START:%.*]]) #[[ATTR0:[0-9]+]] { +; CHECK-NEXT: [[ITER_CHECK:.*]]: +; CHECK-NEXT: [[N_POS:%.*]] = icmp sgt i32 [[N]], 0 +; CHECK-NEXT: call void @llvm.assume(i1 [[N_POS]]) +; CHECK-NEXT: [[N_EXT:%.*]] = zext i32 [[N]] to i64 +; CHECK-NEXT: [[TMP0:%.*]] = add nuw nsw i64 [[N_EXT]], 1 +; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP0]], 4 +; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label %[[VEC_EPILOG_SCALAR_PH:.*]], label %[[VECTOR_MAIN_LOOP_ITER_CHECK:.*]] +; CHECK: [[VECTOR_MAIN_LOOP_ITER_CHECK]]: +; CHECK-NEXT: [[MIN_ITERS_CHECK1:%.*]] = icmp ult i64 [[TMP0]], 16 +; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK1]], label %[[VEC_EPILOG_PH:.*]], label %[[VECTOR_PH:.*]] +; CHECK: [[VECTOR_PH]]: +; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[TMP0]], 16 +; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[TMP0]], [[N_MOD_VF]] +; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> poison, i32 [[START]], i64 0 +; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> poison, <4 x i32> zeroinitializer +; CHECK-NEXT: [[TMP1:%.*]] = icmp eq <4 x i32> [[BROADCAST_SPLAT]], zeroinitializer +; CHECK-NEXT: br label %[[VECTOR_BODY:.*]] +; CHECK: [[VECTOR_BODY]]: +; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <4 x i32> [ splat (i32 -2147483648), %[[VECTOR_PH]] ], [ [[TMP3:%.*]], %[[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI2:%.*]] = phi <4 x i32> [ splat (i32 -2147483648), %[[VECTOR_PH]] ], [ [[TMP4:%.*]], %[[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI3:%.*]] = phi <4 x i32> [ splat (i32 -2147483648), %[[VECTOR_PH]] ], [ [[TMP5:%.*]], %[[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI4:%.*]] = phi <4 x i32> [ splat (i32 -2147483648), %[[VECTOR_PH]] ], [ [[TMP6:%.*]], %[[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_IND:%.*]] = phi <4 x i32> [ <i32 0, i32 1, i32 2, i32 3>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ] +; CHECK-NEXT: [[STEP_ADD:%.*]] = add <4 x i32> [[VEC_IND]], splat (i32 4) +; CHECK-NEXT: [[STEP_ADD_2:%.*]] = add <4 x i32> [[STEP_ADD]], splat (i32 4) +; CHECK-NEXT: [[STEP_ADD_3:%.*]] = add <4 x i32> [[STEP_ADD_2]], splat (i32 4) +; CHECK-NEXT: [[TMP2:%.*]] = extractelement <4 x i1> [[TMP1]], i32 0 +; CHECK-NEXT: [[TMP3]] = select i1 [[TMP2]], <4 x i32> [[VEC_IND]], <4 x i32> [[VEC_PHI]] +; CHECK-NEXT: [[TMP4]] = select i1 [[TMP2]], <4 x i32> [[STEP_ADD]], <4 x i32> [[VEC_PHI2]] +; CHECK-NEXT: [[TMP5]] = select i1 [[TMP2]], <4 x i32> [[STEP_ADD_2]], <4 x i32> [[VEC_PHI3]] +; CHECK-NEXT: [[TMP6]] = select i1 [[TMP2]], <4 x i32> [[STEP_ADD_3]], <4 x i32> [[VEC_PHI4]] +; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 16 +; CHECK-NEXT: [[VEC_IND_NEXT]] = add <4 x i32> [[STEP_ADD_3]], splat (i32 4) +; CHECK-NEXT: [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]] +; CHECK-NEXT: br i1 [[TMP7]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]] +; CHECK: [[MIDDLE_BLOCK]]: +; CHECK-NEXT: [[RDX_MINMAX:%.*]] = call <4 x i32> @llvm.smax.v4i32(<4 x i32> [[TMP3]], <4 x i32> [[TMP4]]) +; CHECK-NEXT: [[RDX_MINMAX5:%.*]] = call <4 x i32> @llvm.smax.v4i32(<4 x i32> [[RDX_MINMAX]], <4 x i32> [[TMP5]]) +; CHECK-NEXT: [[RDX_MINMAX6:%.*]] = call <4 x i32> @llvm.smax.v4i32(<4 x i32> [[RDX_MINMAX5]], <4 x i32> [[TMP6]]) +; CHECK-NEXT: [[TMP8:%.*]] = call i32 @llvm.vector.reduce.smax.v4i32(<4 x i32> [[RDX_MINMAX6]]) +; CHECK-NEXT: [[RDX_SELECT_CMP:%.*]] = icmp ne i32 [[TMP8]], -2147483648 +; CHECK-NEXT: [[RDX_SELECT:%.*]] = select i1 [[RDX_SELECT_CMP]], i32 [[TMP8]], i32 [[START]] +; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[TMP0]], [[N_VEC]] +; CHECK-NEXT: br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[VEC_EPILOG_ITER_CHECK:.*]] +; CHECK: [[VEC_EPILOG_ITER_CHECK]]: +; CHECK-NEXT: [[N_VEC_REMAINING:%.*]] = sub i64 [[TMP0]], [[N_VEC]] +; CHECK-NEXT: [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_VEC_REMAINING]], 4 +; CHECK-NEXT: br i1 [[MIN_EPILOG_ITERS_CHECK]], label %[[VEC_EPILOG_SCALAR_PH]], label %[[VEC_EPILOG_PH]] +; CHECK: [[VEC_EPILOG_PH]]: +; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], %[[VEC_EPILOG_ITER_CHECK]] ], [ 0, %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ] +; CHECK-NEXT: [[BC_MERGE_RDX:%.*]] = phi i32 [ [[RDX_SELECT]], %[[VEC_EPILOG_ITER_CHECK]] ], [ [[START]], %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ] +; CHECK-NEXT: [[TMP9:%.*]] = icmp eq i32 [[BC_MERGE_RDX]], [[START]] +; CHECK-NEXT: [[TMP10:%.*]] = select i1 [[TMP9]], i32 -2147483648, i32 [[BC_MERGE_RDX]] +; CHECK-NEXT: [[N_MOD_VF7:%.*]] = urem i64 [[TMP0]], 4 +; CHECK-NEXT: [[N_VEC8:%.*]] = sub i64 [[TMP0]], [[N_MOD_VF7]] +; CHECK-NEXT: [[BROADCAST_SPLATINSERT9:%.*]] = insertelement <4 x i32> poison, i32 [[START]], i64 0 +; CHECK-NEXT: [[BROADCAST_SPLAT10:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT9]], <4 x i32> poison, <4 x i32> zeroinitializer +; CHECK-NEXT: [[TMP11:%.*]] = icmp eq <4 x i32> [[BROADCAST_SPLAT10]], zeroinitializer +; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <4 x i32> poison, i32 [[TMP10]], i64 0 +; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <4 x i32> [[DOTSPLATINSERT]], <4 x i32> poison, <4 x i32> zeroinitializer +; CHECK-NEXT: [[TMP12:%.*]] = trunc i64 [[BC_RESUME_VAL]] to i32 +; CHECK-NEXT: [[DOTSPLATINSERT13:%.*]] = insertelement <4 x i32> poison, i32 [[TMP12]], i64 0 +; CHECK-NEXT: [[DOTSPLAT14:%.*]] = shufflevector <4 x i32> [[DOTSPLATINSERT13]], <4 x i32> poison, <4 x i32> zeroinitializer +; CHECK-NEXT: [[INDUCTION:%.*]] = add <4 x i32> [[DOTSPLAT14]], <i32 0, i32 1, i32 2, i32 3> +; CHECK-NEXT: br label %[[VEC_EPILOG_VECTOR_BODY:.*]] +; CHECK: [[VEC_EPILOG_VECTOR_BODY]]: +; CHECK-NEXT: [[INDEX11:%.*]] = phi i64 [ [[BC_RESUME_VAL]], %[[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT17:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI12:%.*]] = phi <4 x i32> [ [[DOTSPLAT]], %[[VEC_EPILOG_PH]] ], [ [[TMP14:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_IND15:%.*]] = phi <4 x i32> [ [[INDUCTION]], %[[VEC_EPILOG_PH]] ], [ [[VEC_IND_NEXT16:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ] +; CHECK-NEXT: [[TMP13:%.*]] = extractelement <4 x i1> [[TMP11]], i32 0 +; CHECK-NEXT: [[TMP14]] = select i1 [[TMP13]], <4 x i32> [[VEC_IND15]], <4 x i32> [[VEC_PHI12]] +; CHECK-NEXT: [[INDEX_NEXT17]] = add nuw i64 [[INDEX11]], 4 +; CHECK-NEXT: [[VEC_IND_NEXT16]] = add <4 x i32> [[VEC_IND15]], splat (i32 4) +; CHECK-NEXT: [[TMP15:%.*]] = icmp eq i64 [[INDEX_NEXT17]], [[N_VEC8]] +; CHECK-NEXT: br i1 [[TMP15]], label %[[VEC_EPILOG_MIDDLE_BLOCK:.*]], label %[[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]] +; CHECK: [[VEC_EPILOG_MIDDLE_BLOCK]]: +; CHECK-NEXT: [[TMP16:%.*]] = call i32 @llvm.vector.reduce.smax.v4i32(<4 x i32> [[TMP14]]) +; CHECK-NEXT: [[RDX_SELECT_CMP18:%.*]] = icmp ne i32 [[TMP16]], -2147483648 +; CHECK-NEXT: [[RDX_SELECT19:%.*]] = select i1 [[RDX_SELECT_CMP18]], i32 [[TMP16]], i32 [[START]] +; CHECK-NEXT: [[CMP_N20:%.*]] = icmp eq i64 [[TMP0]], [[N_VEC8]] +; CHECK-NEXT: br i1 [[CMP_N20]], label %[[EXIT]], label %[[VEC_EPILOG_SCALAR_PH]] +; CHECK: [[VEC_EPILOG_SCALAR_PH]]: +; CHECK-NEXT: [[BC_RESUME_VAL21:%.*]] = phi i64 [ [[N_VEC8]], %[[VEC_EPILOG_MIDDLE_BLOCK]] ], [ 0, %[[ITER_CHECK]] ], [ [[N_VEC]], %[[VEC_EPILOG_ITER_CHECK]] ] +; CHECK-NEXT: [[BC_MERGE_RDX22:%.*]] = phi i32 [ [[RDX_SELECT19]], %[[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[START]], %[[ITER_CHECK]] ], [ [[RDX_SELECT]], %[[VEC_EPILOG_ITER_CHECK]] ] +; CHECK-NEXT: br label %[[LOOP:.*]] +; CHECK: [[LOOP]]: +; CHECK-NEXT: [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL21]], %[[VEC_EPILOG_SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ] +; CHECK-NEXT: [[RED:%.*]] = phi i32 [ [[BC_MERGE_RDX22]], %[[VEC_EPILOG_SCALAR_PH]] ], [ [[RED_NEXT:%.*]], %[[LOOP]] ] +; CHECK-NEXT: [[C:%.*]] = icmp eq i32 [[START]], 0 +; CHECK-NEXT: [[IV_TRUNC:%.*]] = trunc i64 [[IV]] to i32 +; CHECK-NEXT: [[RED_NEXT]] = select i1 [[C]], i32 [[IV_TRUNC]], i32 [[RED]] +; CHECK-NEXT: [[IV_NEXT]] = add i64 [[IV]], 1 +; CHECK-NEXT: [[EC:%.*]] = icmp eq i64 [[IV]], [[N_EXT]] +; CHECK-NEXT: br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP7:![0-9]+]] +; CHECK: [[EXIT]]: +; CHECK-NEXT: [[RED_NEXT_LCSSA:%.*]] = phi i32 [ [[RED_NEXT]], %[[LOOP]] ], [ [[RDX_SELECT]], %[[MIDDLE_BLOCK]] ], [ [[RDX_SELECT19]], %[[VEC_EPILOG_MIDDLE_BLOCK]] ] +; CHECK-NEXT: ret i32 [[RED_NEXT_LCSSA]] +; +entry: + %N.pos = icmp sgt i32 %N, 0 + call void @llvm.assume(i1 %N.pos) + %N.ext = zext i32 %N to i64 + br label %loop + +loop: + %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ] + %red = phi i32 [ %start, %entry ], [ %red.next, %loop ] + %c = icmp eq i32 %start, 0 + %iv.trunc = trunc i64 %iv to i32 + %red.next = select i1 %c, i32 %iv.trunc, i32 %red + %iv.next = add i64 %iv, 1 + %ec = icmp eq i64 %iv, %N.ext + br i1 %ec, label %exit, label %loop + +exit: + ret i32 %red.next +} + +declare void @llvm.assume(i1 noundef) + +attributes #0 = { "target-cpu"="apple-m1" } diff --git a/llvm/test/Transforms/LoopVectorize/epilog-iv-select-cmp.ll b/llvm/test/Transforms/LoopVectorize/epilog-iv-select-cmp.ll index 06f0f05889116..9c426a71fb0c9 100644 --- a/llvm/test/Transforms/LoopVectorize/epilog-iv-select-cmp.ll +++ b/llvm/test/Transforms/LoopVectorize/epilog-iv-select-cmp.ll @@ -1,4 +1,4 @@ -; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5 +; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --version 5 ; RUN: opt -passes=loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -epilogue-vectorization-force-VF=4 -S < %s | FileCheck %s define i64 @select_icmp_const(ptr %a, i64 %n) { @@ -212,13 +212,118 @@ loop: exit: ret i64 %sel } -;. -; CHECK: [[LOOP0]] = distinct !{[[LOOP0]], [[META1:![0-9]+]], [[META2:![0-9]+]]} -; CHECK: [[META1]] = !{!"llvm.loop.isvectorized", i32 1} -; CHECK: [[META2]] = !{!"llvm.loop.unroll.runtime.disable"} -; CHECK: [[LOOP3]] = distinct !{[[LOOP3]], [[META1]], [[META2]]} -; CHECK: [[LOOP4]] = distinct !{[[LOOP4]], [[META2]], [[META1]]} -; CHECK: [[LOOP5]] = distinct !{[[LOOP5]], [[META1]], [[META2]]} -; CHECK: [[LOOP6]] = distinct !{[[LOOP6]], [[META1]], [[META2]]} -; CHECK: [[LOOP7]] = distinct !{[[LOOP7]], [[META2]], [[META1]]} -;. + +define i8 @select_icmp_var_start(ptr %a, i8 %n, i8 %start) { +; CHECK-LABEL: define i8 @select_icmp_var_start( +; CHECK-SAME: ptr [[A:%.*]], i8 [[N:%.*]], i8 [[START:%.*]]) { +; CHECK-NEXT: [[ITER_CHECK:.*]]: +; CHECK-NEXT: [[TMP0:%.*]] = add i8 [[N]], -1 +; CHECK-NEXT: [[TMP1:%.*]] = zext i8 [[TMP0]] to i32 +; CHECK-NEXT: [[TMP2:%.*]] = add nuw nsw i32 [[TMP1]], 1 +; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[TMP2]], 4 +; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label %[[VEC_EPILOG_SCALAR_PH:.*]], label %[[VECTOR_MAIN_LOOP_ITER_CHECK:.*]] +; CHECK: [[VECTOR_MAIN_LOOP_ITER_CHECK]]: +; CHECK-NEXT: [[MIN_ITERS_CHECK1:%.*]] = icmp ult i32 [[TMP2]], 4 +; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK1]], label %[[VEC_EPILOG_PH:.*]], label %[[VECTOR_PH:.*]] +; CHECK: [[VECTOR_PH]]: +; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i32 [[TMP2]], 4 +; CHECK-NEXT: [[N_VEC:%.*]] = sub i32 [[TMP2]], [[N_MOD_VF]] +; CHECK-NEXT: [[TMP3:%.*]] = trunc i32 [[N_VEC]] to i8 +; CHECK-NEXT: br label %[[VECTOR_BODY:.*]] +; CHECK: [[VECTOR_BODY]]: +; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_IND:%.*]] = phi <4 x i8> [ <i8 0, i8 1, i8 2, i8 3>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <4 x i8> [ splat (i8 -128), %[[VECTOR_PH]] ], [ [[TMP8:%.*]], %[[VECTOR_BODY]] ] +; CHECK-NEXT: [[TMP4:%.*]] = trunc i32 [[INDEX]] to i8 +; CHECK-NEXT: [[TMP20:%.*]] = add i8 [[TMP4]], 0 +; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds i8, ptr [[A]], i8 [[TMP20]] +; CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds i8, ptr [[TMP5]], i32 0 +; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i8>, ptr [[TMP6]], align 8 +; CHECK-NEXT: [[TMP7:%.*]] = icmp eq <4 x i8> [[WIDE_LOAD]], splat (i8 3) +; CHECK-NEXT: [[TMP8]] = select <4 x i1> [[TMP7]], <4 x i8> [[VEC_IND]], <4 x i8> [[VEC_PHI]] +; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4 +; CHECK-NEXT: [[VEC_IND_NEXT]] = add <4 x i8> [[VEC_IND]], splat (i8 4) +; CHECK-NEXT: [[TMP9:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]] +; CHECK-NEXT: br i1 [[TMP9]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]] +; CHECK: [[MIDDLE_BLOCK]]: +; CHECK-NEXT: [[TMP10:%.*]] = call i8 @llvm.vector.reduce.smax.v4i8(<4 x i8> [[TMP8]]) +; CHECK-NEXT: [[RDX_SELECT_CMP:%.*]] = icmp ne i8 [[TMP10]], -128 +; CHECK-NEXT: [[RDX_SELECT:%.*]] = select i1 [[RDX_SELECT_CMP]], i8 [[TMP10]], i8 [[START]] +; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i32 [[TMP2]], [[N_VEC]] +; CHECK-NEXT: br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[VEC_EPILOG_ITER_CHECK:.*]] +; CHECK: [[VEC_EPILOG_ITER_CHECK]]: +; CHECK-NEXT: [[IND_END:%.*]] = trunc i32 [[N_VEC]] to i8 +; CHECK-NEXT: [[N_VEC_REMAINING:%.*]] = sub i32 [[TMP2]], [[N_VEC]] +; CHECK-NEXT: [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i32 [[N_VEC_REMAINING]], 4 +; CHECK-NEXT: br i1 [[MIN_EPILOG_ITERS_CHECK]], label %[[VEC_EPILOG_SCALAR_PH]], label %[[VEC_EPILOG_PH]] +; CHECK: [[VEC_EPILOG_PH]]: +; CHECK-NEXT: [[VEC_EPILOG_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], %[[VEC_EPILOG_ITER_CHECK]] ], [ 0, %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ] +; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i8 [ [[TMP3]], %[[VEC_EPILOG_ITER_CHECK]] ], [ 0, %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ] +; CHECK-NEXT: [[BC_MERGE_RDX:%.*]] = phi i8 [ [[RDX_SELECT]], %[[VEC_EPILOG_ITER_CHECK]] ], [ [[START]], %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ] +; CHECK-NEXT: [[TMP11:%.*]] = icmp eq i8 [[BC_MERGE_RDX]], [[START]] +; CHECK-NEXT: [[TMP12:%.*]] = select i1 [[TMP11]], i8 -128, i8 [[BC_MERGE_RDX]] +; CHECK-NEXT: [[N_MOD_VF2:%.*]] = urem i32 [[TMP2]], 4 +; CHECK-NEXT: [[N_VEC3:%.*]] = sub i32 [[TMP2]], [[N_MOD_VF2]] +; CHECK-NEXT: [[TMP13:%.*]] = trunc i32 [[N_VEC3]] to i8 +; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <4 x i8> poison, i8 [[BC_RESUME_VAL]], i64 0 +; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <4 x i8> [[DOTSPLATINSERT]], <4 x i8> poison, <4 x i32> zeroinitializer +; CHECK-NEXT: [[INDUCTION:%.*]] = add <4 x i8> [[DOTSPLAT]], <i8 0, i8 1, i8 2, i8 3> +; CHECK-NEXT: [[DOTSPLATINSERT8:%.*]] = insertelement <4 x i8> poison, i8 [[TMP12]], i64 0 +; CHECK-NEXT: [[DOTSPLAT9:%.*]] = shufflevector <4 x i8> [[DOTSPLATINSERT8]], <4 x i8> poison, <4 x i32> zeroinitializer +; CHECK-NEXT: br label %[[VEC_EPILOG_VECTOR_BODY:.*]] +; CHECK: [[VEC_EPILOG_VECTOR_BODY]]: +; CHECK-NEXT: [[INDEX4:%.*]] = phi i32 [ [[VEC_EPILOG_RESUME_VAL]], %[[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT11:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_IND5:%.*]] = phi <4 x i8> [ [[INDUCTION]], %[[VEC_EPILOG_PH]] ], [ [[VEC_IND_NEXT6:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI7:%.*]] = phi <4 x i8> [ [[DOTSPLAT9]], %[[VEC_EPILOG_PH]] ], [ [[TMP17:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ] +; CHECK-NEXT: [[OFFSET_IDX:%.*]] = trunc i32 [[INDEX4]] to i8 +; CHECK-NEXT: [[TMP21:%.*]] = add i8 [[OFFSET_IDX]], 0 +; CHECK-NEXT: [[TMP14:%.*]] = getelementptr inbounds i8, ptr [[A]], i8 [[TMP21]] +; CHECK-NEXT: [[TMP15:%.*]] = getelementptr inbounds i8, ptr [[TMP14]], i32 0 +; CHECK-NEXT: [[WIDE_LOAD10:%.*]] = load <4 x i8>, ptr [[TMP15]], align 8 +; CHECK-NEXT: [[TMP16:%.*]] = icmp eq <4 x i8> [[WIDE_LOAD10]], splat (i8 3) +; CHECK-NEXT: [[TMP17]] = select <4 x i1> [[TMP16]], <4 x i8> [[VEC_IND5]], <4 x i8> [[VEC_PHI7]] +; CHECK-NEXT: [[INDEX_NEXT11]] = add nuw i32 [[INDEX4]], 4 +; CHECK-NEXT: [[VEC_IND_NEXT6]] = add <4 x i8> [[VEC_IND5]], splat (i8 4) +; CHECK-NEXT: [[TMP18:%.*]] = icmp eq i32 [[INDEX_NEXT11]], [[N_VEC3]] +; CHECK-NEXT: br i1 [[TMP18]], label %[[VEC_EPILOG_MIDDLE_BLOCK:.*]], label %[[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP9:![0-9]+]] +; CHECK: [[VEC_EPILOG_MIDDLE_BLOCK]]: +; CHECK-NEXT: [[TMP19:%.*]] = call i8 @llvm.vector.reduce.smax.v4i8(<4 x i8> [[TMP17]]) +; CHECK-NEXT: [[RDX_SELECT_CMP12:%.*]] = icmp ne i8 [[TMP19]], -128 +; CHECK-NEXT: [[RDX_SELECT13:%.*]] = select i1 [[RDX_SELECT_CMP12]], i8 [[TMP19]], i8 [[START]] +; CHECK-NEXT: [[CMP_N14:%.*]] = icmp eq i32 [[TMP2]], [[N_VEC3]] +; CHECK-NEXT: br i1 [[CMP_N14]], label %[[EXIT]], label %[[VEC_EPILOG_SCALAR_PH]] +; CHECK: [[VEC_EPILOG_SCALAR_PH]]: +; CHECK-NEXT: [[BC_RESUME_VAL15:%.*]] = phi i8 [ [[TMP13]], %[[VEC_EPILOG_MIDDLE_BLOCK]] ], [ 0, %[[ITER_CHECK]] ], [ [[IND_END]], %[[VEC_EPILOG_ITER_CHECK]] ] +; CHECK-NEXT: [[BC_MERGE_RDX16:%.*]] = phi i8 [ [[RDX_SELECT13]], %[[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[START]], %[[ITER_CHECK]] ], [ [[RDX_SELECT]], %[[VEC_EPILOG_ITER_CHECK]] ] +; CHECK-NEXT: br label %[[LOOP:.*]] +; CHECK: [[LOOP]]: +; CHECK-NEXT: [[IV:%.*]] = phi i8 [ [[BC_RESUME_VAL15]], %[[VEC_EPILOG_SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ] +; CHECK-NEXT: [[RDX:%.*]] = phi i8 [ [[BC_MERGE_RDX16]], %[[VEC_EPILOG_SCALAR_PH]] ], [ [[SEL:%.*]], %[[LOOP]] ] +; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds i8, ptr [[A]], i8 [[IV]] +; CHECK-NEXT: [[L:%.*]] = load i8, ptr [[GEP]], align 8 +; CHECK-NEXT: [[C:%.*]] = icmp eq i8 [[L]], 3 +; CHECK-NEXT: [[SEL]] = select i1 [[C]], i8 [[IV]], i8 [[RDX]] +; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i8 [[IV]], 1 +; CHECK-NEXT: [[EC:%.*]] = icmp eq i8 [[IV_NEXT]], [[N]] +; CHECK-NEXT: br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP10:![0-9]+]] +; CHECK: [[EXIT]]: +; CHECK-NEXT: [[SEL_LCSSA:%.*]] = phi i8 [ [[SEL]], %[[LOOP]] ], [ [[RDX_SELECT]], %[[MIDDLE_BLOCK]] ], [ [[RDX_SELECT13]], %[[VEC_EPILOG_MIDDLE_BLOCK]] ] +; CHECK-NEXT: ret i8 [[SEL_LCSSA]] +; +entry: + br label %loop + +loop: + %iv = phi i8 [ 0, %entry ], [ %iv.next, %loop ] + %rdx = phi i8 [ %start, %entry ], [ %sel, %loop ] + %gep = getelementptr inbounds i8, ptr %a, i8 %iv + %l = load i8, ptr %gep, align 8 + %c = icmp eq i8 %l, 3 + %sel = select i1 %c, i8 %iv, i8 %rdx + %iv.next = add nuw nsw i8 %iv, 1 + %ec = icmp eq i8 %iv.next, %n + br i1 %ec, label %exit, label %loop + +exit: + ret i8 %sel +} >From 4b3162dbec826d6090fe5381d85a8125cba549e3 Mon Sep 17 00:00:00 2001 From: Florian Hahn <f...@fhahn.com> Date: Mon, 14 Apr 2025 17:18:11 +0100 Subject: [PATCH 2/2] [LV] Disable epilogue vectorization for FindLastIV if start is poison. Back-porting properly freezing of the start value during epilogue vectorization (2bdc1a1337) is non-trivial. For the 20.x release, just disable epilogue vectorization for FindLastIV reductions where the start value may be poison or undef. Fixes #126836. --- .../Transforms/Vectorize/LoopVectorize.cpp | 10 ++ .../AArch64/epilog-iv-select-cmp.ll | 130 ++++-------------- .../LoopVectorize/epilog-iv-select-cmp.ll | 78 +++-------- 3 files changed, 50 insertions(+), 168 deletions(-) diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp index 7cd395255163a..1baec6d6ca37b 100644 --- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp +++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp @@ -4626,6 +4626,16 @@ bool LoopVectorizationPlanner::isCandidateForEpilogueVectorization( return false; } + // Don't vectorize the epilogue, if there are FindLastIV recurrences with a + // start value may be undef or poison. Such start values would need freezing. + if (any_of(Legal->getReductionVars(), [](const auto &P) { + return RecurrenceDescriptor::isFindLastIVRecurrenceKind( + P.second.getRecurrenceKind()) && + !isGuaranteedNotToBeUndefOrPoison( + P.second.getRecurrenceStartValue()); + })) + return false; + // Epilogue vectorization code has not been auditted to ensure it handles // non-latch exits properly. It may be fine, but it needs auditted and // tested. diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/epilog-iv-select-cmp.ll b/llvm/test/Transforms/LoopVectorize/AArch64/epilog-iv-select-cmp.ll index b2643aa11d1fd..7355aed6ae65f 100644 --- a/llvm/test/Transforms/LoopVectorize/AArch64/epilog-iv-select-cmp.ll +++ b/llvm/test/Transforms/LoopVectorize/AArch64/epilog-iv-select-cmp.ll @@ -4,15 +4,12 @@ define i8 @select_icmp_var_start(ptr %a, i8 %n, i8 %start) { ; CHECK-LABEL: define i8 @select_icmp_var_start( ; CHECK-SAME: ptr [[A:%.*]], i8 [[N:%.*]], i8 [[START:%.*]]) { -; CHECK-NEXT: [[ITER_CHECK:.*]]: +; CHECK-NEXT: [[ENTRY:.*]]: ; CHECK-NEXT: [[TMP0:%.*]] = add i8 [[N]], -1 ; CHECK-NEXT: [[TMP1:%.*]] = zext i8 [[TMP0]] to i32 ; CHECK-NEXT: [[TMP2:%.*]] = add nuw nsw i32 [[TMP1]], 1 -; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[TMP2]], 8 -; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label %[[VEC_EPILOG_SCALAR_PH:.*]], label %[[VECTOR_MAIN_LOOP_ITER_CHECK:.*]] -; CHECK: [[VECTOR_MAIN_LOOP_ITER_CHECK]]: ; CHECK-NEXT: [[MIN_ITERS_CHECK1:%.*]] = icmp ult i32 [[TMP2]], 32 -; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK1]], label %[[VEC_EPILOG_PH:.*]], label %[[VECTOR_PH:.*]] +; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK1]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]] ; CHECK: [[VECTOR_PH]]: ; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i32 [[TMP2]], 32 ; CHECK-NEXT: [[N_VEC:%.*]] = sub i32 [[TMP2]], [[N_MOD_VF]] @@ -45,64 +42,23 @@ define i8 @select_icmp_var_start(ptr %a, i8 %n, i8 %start) { ; CHECK-NEXT: [[RDX_SELECT_CMP12:%.*]] = icmp ne i8 [[TMP13]], -128 ; CHECK-NEXT: [[RDX_SELECT:%.*]] = select i1 [[RDX_SELECT_CMP12]], i8 [[TMP13]], i8 [[START]] ; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i32 [[TMP2]], [[N_VEC]] -; CHECK-NEXT: br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[VEC_EPILOG_ITER_CHECK:.*]] -; CHECK: [[VEC_EPILOG_ITER_CHECK]]: -; CHECK-NEXT: [[IND_END:%.*]] = trunc i32 [[N_VEC]] to i8 -; CHECK-NEXT: [[N_VEC_REMAINING:%.*]] = sub i32 [[TMP2]], [[N_VEC]] -; CHECK-NEXT: [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i32 [[N_VEC_REMAINING]], 8 -; CHECK-NEXT: br i1 [[MIN_EPILOG_ITERS_CHECK]], label %[[VEC_EPILOG_SCALAR_PH]], label %[[VEC_EPILOG_PH]] -; CHECK: [[VEC_EPILOG_PH]]: -; CHECK-NEXT: [[VEC_EPILOG_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], %[[VEC_EPILOG_ITER_CHECK]] ], [ 0, %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ] -; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i8 [ [[TMP3]], %[[VEC_EPILOG_ITER_CHECK]] ], [ 0, %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ] -; CHECK-NEXT: [[BC_MERGE_RDX:%.*]] = phi i8 [ [[RDX_SELECT]], %[[VEC_EPILOG_ITER_CHECK]] ], [ [[START]], %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ] -; CHECK-NEXT: [[TMP14:%.*]] = icmp eq i8 [[BC_MERGE_RDX]], [[START]] -; CHECK-NEXT: [[TMP15:%.*]] = select i1 [[TMP14]], i8 -128, i8 [[BC_MERGE_RDX]] -; CHECK-NEXT: [[N_MOD_VF4:%.*]] = urem i32 [[TMP2]], 8 -; CHECK-NEXT: [[N_VEC5:%.*]] = sub i32 [[TMP2]], [[N_MOD_VF4]] -; CHECK-NEXT: [[TMP16:%.*]] = trunc i32 [[N_VEC5]] to i8 -; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <8 x i8> poison, i8 [[BC_RESUME_VAL]], i64 0 -; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <8 x i8> [[DOTSPLATINSERT]], <8 x i8> poison, <8 x i32> zeroinitializer -; CHECK-NEXT: [[INDUCTION:%.*]] = add <8 x i8> [[DOTSPLAT]], <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7> -; CHECK-NEXT: [[DOTSPLATINSERT10:%.*]] = insertelement <8 x i8> poison, i8 [[TMP15]], i64 0 -; CHECK-NEXT: [[DOTSPLAT11:%.*]] = shufflevector <8 x i8> [[DOTSPLATINSERT10]], <8 x i8> poison, <8 x i32> zeroinitializer -; CHECK-NEXT: br label %[[VEC_EPILOG_VECTOR_BODY:.*]] -; CHECK: [[VEC_EPILOG_VECTOR_BODY]]: -; CHECK-NEXT: [[INDEX6:%.*]] = phi i32 [ [[VEC_EPILOG_RESUME_VAL]], %[[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT13:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ] -; CHECK-NEXT: [[VEC_IND7:%.*]] = phi <8 x i8> [ [[INDUCTION]], %[[VEC_EPILOG_PH]] ], [ [[VEC_IND_NEXT8:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ] -; CHECK-NEXT: [[VEC_PHI9:%.*]] = phi <8 x i8> [ [[DOTSPLAT11]], %[[VEC_EPILOG_PH]] ], [ [[TMP20:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ] -; CHECK-NEXT: [[IV:%.*]] = trunc i32 [[INDEX6]] to i8 -; CHECK-NEXT: [[TMP24:%.*]] = add i8 [[IV]], 0 -; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds i8, ptr [[A]], i8 [[TMP24]] -; CHECK-NEXT: [[TMP18:%.*]] = getelementptr inbounds i8, ptr [[GEP]], i32 0 -; CHECK-NEXT: [[WIDE_LOAD12:%.*]] = load <8 x i8>, ptr [[TMP18]], align 8 -; CHECK-NEXT: [[TMP19:%.*]] = icmp eq <8 x i8> [[WIDE_LOAD12]], splat (i8 3) -; CHECK-NEXT: [[TMP20]] = select <8 x i1> [[TMP19]], <8 x i8> [[VEC_IND7]], <8 x i8> [[VEC_PHI9]] -; CHECK-NEXT: [[INDEX_NEXT13]] = add nuw i32 [[INDEX6]], 8 -; CHECK-NEXT: [[VEC_IND_NEXT8]] = add <8 x i8> [[VEC_IND7]], splat (i8 8) -; CHECK-NEXT: [[TMP21:%.*]] = icmp eq i32 [[INDEX_NEXT13]], [[N_VEC5]] -; CHECK-NEXT: br i1 [[TMP21]], label %[[VEC_EPILOG_MIDDLE_BLOCK:.*]], label %[[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]] -; CHECK: [[VEC_EPILOG_MIDDLE_BLOCK]]: -; CHECK-NEXT: [[TMP22:%.*]] = call i8 @llvm.vector.reduce.smax.v8i8(<8 x i8> [[TMP20]]) -; CHECK-NEXT: [[RDX_SELECT_CMP14:%.*]] = icmp ne i8 [[TMP22]], -128 -; CHECK-NEXT: [[RDX_SELECT15:%.*]] = select i1 [[RDX_SELECT_CMP14]], i8 [[TMP22]], i8 [[START]] -; CHECK-NEXT: [[CMP_N16:%.*]] = icmp eq i32 [[TMP2]], [[N_VEC5]] -; CHECK-NEXT: br i1 [[CMP_N16]], label %[[EXIT]], label %[[VEC_EPILOG_SCALAR_PH]] -; CHECK: [[VEC_EPILOG_SCALAR_PH]]: -; CHECK-NEXT: [[BC_RESUME_VAL17:%.*]] = phi i8 [ [[TMP16]], %[[VEC_EPILOG_MIDDLE_BLOCK]] ], [ 0, %[[ITER_CHECK]] ], [ [[IND_END]], %[[VEC_EPILOG_ITER_CHECK]] ] -; CHECK-NEXT: [[BC_MERGE_RDX18:%.*]] = phi i8 [ [[RDX_SELECT15]], %[[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[START]], %[[ITER_CHECK]] ], [ [[RDX_SELECT]], %[[VEC_EPILOG_ITER_CHECK]] ] +; CHECK-NEXT: br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[SCALAR_PH]] +; CHECK: [[SCALAR_PH]]: +; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i8 [ [[TMP3]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ] +; CHECK-NEXT: [[BC_MERGE_RDX:%.*]] = phi i8 [ [[RDX_SELECT]], %[[MIDDLE_BLOCK]] ], [ [[START]], %[[ENTRY]] ] ; CHECK-NEXT: br label %[[LOOP:.*]] ; CHECK: [[LOOP]]: -; CHECK-NEXT: [[IV1:%.*]] = phi i8 [ [[BC_RESUME_VAL17]], %[[VEC_EPILOG_SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ] -; CHECK-NEXT: [[RDX:%.*]] = phi i8 [ [[BC_MERGE_RDX18]], %[[VEC_EPILOG_SCALAR_PH]] ], [ [[SEL:%.*]], %[[LOOP]] ] +; CHECK-NEXT: [[IV1:%.*]] = phi i8 [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ] +; CHECK-NEXT: [[RDX:%.*]] = phi i8 [ [[BC_MERGE_RDX]], %[[SCALAR_PH]] ], [ [[SEL:%.*]], %[[LOOP]] ] ; CHECK-NEXT: [[GEP1:%.*]] = getelementptr inbounds i8, ptr [[A]], i8 [[IV1]] ; CHECK-NEXT: [[L:%.*]] = load i8, ptr [[GEP1]], align 8 ; CHECK-NEXT: [[C:%.*]] = icmp eq i8 [[L]], 3 ; CHECK-NEXT: [[SEL]] = select i1 [[C]], i8 [[IV1]], i8 [[RDX]] ; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i8 [[IV1]], 1 ; CHECK-NEXT: [[EC:%.*]] = icmp eq i8 [[IV_NEXT]], [[N]] -; CHECK-NEXT: br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP4:![0-9]+]] +; CHECK-NEXT: br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP3:![0-9]+]] ; CHECK: [[EXIT]]: -; CHECK-NEXT: [[SEL_LCSSA:%.*]] = phi i8 [ [[SEL]], %[[LOOP]] ], [ [[RDX_SELECT]], %[[MIDDLE_BLOCK]] ], [ [[RDX_SELECT15]], %[[VEC_EPILOG_MIDDLE_BLOCK]] ] +; CHECK-NEXT: [[SEL_LCSSA:%.*]] = phi i8 [ [[SEL]], %[[LOOP]] ], [ [[RDX_SELECT]], %[[MIDDLE_BLOCK]] ] ; CHECK-NEXT: ret i8 [[SEL_LCSSA]] ; entry: @@ -126,16 +82,13 @@ exit: define i32 @select_icmp_var_start_iv_trunc(i32 %N, i32 %start) #0 { ; CHECK-LABEL: define i32 @select_icmp_var_start_iv_trunc( ; CHECK-SAME: i32 [[N:%.*]], i32 [[START:%.*]]) #[[ATTR0:[0-9]+]] { -; CHECK-NEXT: [[ITER_CHECK:.*]]: +; CHECK-NEXT: [[ENTRY:.*]]: ; CHECK-NEXT: [[N_POS:%.*]] = icmp sgt i32 [[N]], 0 ; CHECK-NEXT: call void @llvm.assume(i1 [[N_POS]]) ; CHECK-NEXT: [[N_EXT:%.*]] = zext i32 [[N]] to i64 ; CHECK-NEXT: [[TMP0:%.*]] = add nuw nsw i64 [[N_EXT]], 1 -; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP0]], 4 -; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label %[[VEC_EPILOG_SCALAR_PH:.*]], label %[[VECTOR_MAIN_LOOP_ITER_CHECK:.*]] -; CHECK: [[VECTOR_MAIN_LOOP_ITER_CHECK]]: ; CHECK-NEXT: [[MIN_ITERS_CHECK1:%.*]] = icmp ult i64 [[TMP0]], 16 -; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK1]], label %[[VEC_EPILOG_PH:.*]], label %[[VECTOR_PH:.*]] +; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK1]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]] ; CHECK: [[VECTOR_PH]]: ; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[TMP0]], 16 ; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[TMP0]], [[N_MOD_VF]] @@ -161,68 +114,31 @@ define i32 @select_icmp_var_start_iv_trunc(i32 %N, i32 %start) #0 { ; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 16 ; CHECK-NEXT: [[VEC_IND_NEXT]] = add <4 x i32> [[STEP_ADD_3]], splat (i32 4) ; CHECK-NEXT: [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]] -; CHECK-NEXT: br i1 [[TMP7]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]] +; CHECK-NEXT: br i1 [[TMP7]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]] ; CHECK: [[MIDDLE_BLOCK]]: ; CHECK-NEXT: [[RDX_MINMAX:%.*]] = call <4 x i32> @llvm.smax.v4i32(<4 x i32> [[TMP3]], <4 x i32> [[TMP4]]) ; CHECK-NEXT: [[RDX_MINMAX5:%.*]] = call <4 x i32> @llvm.smax.v4i32(<4 x i32> [[RDX_MINMAX]], <4 x i32> [[TMP5]]) ; CHECK-NEXT: [[RDX_MINMAX6:%.*]] = call <4 x i32> @llvm.smax.v4i32(<4 x i32> [[RDX_MINMAX5]], <4 x i32> [[TMP6]]) -; CHECK-NEXT: [[TMP8:%.*]] = call i32 @llvm.vector.reduce.smax.v4i32(<4 x i32> [[RDX_MINMAX6]]) -; CHECK-NEXT: [[RDX_SELECT_CMP:%.*]] = icmp ne i32 [[TMP8]], -2147483648 -; CHECK-NEXT: [[RDX_SELECT:%.*]] = select i1 [[RDX_SELECT_CMP]], i32 [[TMP8]], i32 [[START]] -; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[TMP0]], [[N_VEC]] -; CHECK-NEXT: br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[VEC_EPILOG_ITER_CHECK:.*]] -; CHECK: [[VEC_EPILOG_ITER_CHECK]]: -; CHECK-NEXT: [[N_VEC_REMAINING:%.*]] = sub i64 [[TMP0]], [[N_VEC]] -; CHECK-NEXT: [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_VEC_REMAINING]], 4 -; CHECK-NEXT: br i1 [[MIN_EPILOG_ITERS_CHECK]], label %[[VEC_EPILOG_SCALAR_PH]], label %[[VEC_EPILOG_PH]] -; CHECK: [[VEC_EPILOG_PH]]: -; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], %[[VEC_EPILOG_ITER_CHECK]] ], [ 0, %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ] -; CHECK-NEXT: [[BC_MERGE_RDX:%.*]] = phi i32 [ [[RDX_SELECT]], %[[VEC_EPILOG_ITER_CHECK]] ], [ [[START]], %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ] -; CHECK-NEXT: [[TMP9:%.*]] = icmp eq i32 [[BC_MERGE_RDX]], [[START]] -; CHECK-NEXT: [[TMP10:%.*]] = select i1 [[TMP9]], i32 -2147483648, i32 [[BC_MERGE_RDX]] -; CHECK-NEXT: [[N_MOD_VF7:%.*]] = urem i64 [[TMP0]], 4 -; CHECK-NEXT: [[N_VEC8:%.*]] = sub i64 [[TMP0]], [[N_MOD_VF7]] -; CHECK-NEXT: [[BROADCAST_SPLATINSERT9:%.*]] = insertelement <4 x i32> poison, i32 [[START]], i64 0 -; CHECK-NEXT: [[BROADCAST_SPLAT10:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT9]], <4 x i32> poison, <4 x i32> zeroinitializer -; CHECK-NEXT: [[TMP11:%.*]] = icmp eq <4 x i32> [[BROADCAST_SPLAT10]], zeroinitializer -; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <4 x i32> poison, i32 [[TMP10]], i64 0 -; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <4 x i32> [[DOTSPLATINSERT]], <4 x i32> poison, <4 x i32> zeroinitializer -; CHECK-NEXT: [[TMP12:%.*]] = trunc i64 [[BC_RESUME_VAL]] to i32 -; CHECK-NEXT: [[DOTSPLATINSERT13:%.*]] = insertelement <4 x i32> poison, i32 [[TMP12]], i64 0 -; CHECK-NEXT: [[DOTSPLAT14:%.*]] = shufflevector <4 x i32> [[DOTSPLATINSERT13]], <4 x i32> poison, <4 x i32> zeroinitializer -; CHECK-NEXT: [[INDUCTION:%.*]] = add <4 x i32> [[DOTSPLAT14]], <i32 0, i32 1, i32 2, i32 3> -; CHECK-NEXT: br label %[[VEC_EPILOG_VECTOR_BODY:.*]] -; CHECK: [[VEC_EPILOG_VECTOR_BODY]]: -; CHECK-NEXT: [[INDEX11:%.*]] = phi i64 [ [[BC_RESUME_VAL]], %[[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT17:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ] -; CHECK-NEXT: [[VEC_PHI12:%.*]] = phi <4 x i32> [ [[DOTSPLAT]], %[[VEC_EPILOG_PH]] ], [ [[TMP14:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ] -; CHECK-NEXT: [[VEC_IND15:%.*]] = phi <4 x i32> [ [[INDUCTION]], %[[VEC_EPILOG_PH]] ], [ [[VEC_IND_NEXT16:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ] -; CHECK-NEXT: [[TMP13:%.*]] = extractelement <4 x i1> [[TMP11]], i32 0 -; CHECK-NEXT: [[TMP14]] = select i1 [[TMP13]], <4 x i32> [[VEC_IND15]], <4 x i32> [[VEC_PHI12]] -; CHECK-NEXT: [[INDEX_NEXT17]] = add nuw i64 [[INDEX11]], 4 -; CHECK-NEXT: [[VEC_IND_NEXT16]] = add <4 x i32> [[VEC_IND15]], splat (i32 4) -; CHECK-NEXT: [[TMP15:%.*]] = icmp eq i64 [[INDEX_NEXT17]], [[N_VEC8]] -; CHECK-NEXT: br i1 [[TMP15]], label %[[VEC_EPILOG_MIDDLE_BLOCK:.*]], label %[[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]] -; CHECK: [[VEC_EPILOG_MIDDLE_BLOCK]]: -; CHECK-NEXT: [[TMP16:%.*]] = call i32 @llvm.vector.reduce.smax.v4i32(<4 x i32> [[TMP14]]) +; CHECK-NEXT: [[TMP16:%.*]] = call i32 @llvm.vector.reduce.smax.v4i32(<4 x i32> [[RDX_MINMAX6]]) ; CHECK-NEXT: [[RDX_SELECT_CMP18:%.*]] = icmp ne i32 [[TMP16]], -2147483648 ; CHECK-NEXT: [[RDX_SELECT19:%.*]] = select i1 [[RDX_SELECT_CMP18]], i32 [[TMP16]], i32 [[START]] -; CHECK-NEXT: [[CMP_N20:%.*]] = icmp eq i64 [[TMP0]], [[N_VEC8]] -; CHECK-NEXT: br i1 [[CMP_N20]], label %[[EXIT]], label %[[VEC_EPILOG_SCALAR_PH]] -; CHECK: [[VEC_EPILOG_SCALAR_PH]]: -; CHECK-NEXT: [[BC_RESUME_VAL21:%.*]] = phi i64 [ [[N_VEC8]], %[[VEC_EPILOG_MIDDLE_BLOCK]] ], [ 0, %[[ITER_CHECK]] ], [ [[N_VEC]], %[[VEC_EPILOG_ITER_CHECK]] ] -; CHECK-NEXT: [[BC_MERGE_RDX22:%.*]] = phi i32 [ [[RDX_SELECT19]], %[[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[START]], %[[ITER_CHECK]] ], [ [[RDX_SELECT]], %[[VEC_EPILOG_ITER_CHECK]] ] +; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[TMP0]], [[N_VEC]] +; CHECK-NEXT: br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[SCALAR_PH]] +; CHECK: [[SCALAR_PH]]: +; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ] +; CHECK-NEXT: [[BC_MERGE_RDX:%.*]] = phi i32 [ [[RDX_SELECT19]], %[[MIDDLE_BLOCK]] ], [ [[START]], %[[ENTRY]] ] ; CHECK-NEXT: br label %[[LOOP:.*]] ; CHECK: [[LOOP]]: -; CHECK-NEXT: [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL21]], %[[VEC_EPILOG_SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ] -; CHECK-NEXT: [[RED:%.*]] = phi i32 [ [[BC_MERGE_RDX22]], %[[VEC_EPILOG_SCALAR_PH]] ], [ [[RED_NEXT:%.*]], %[[LOOP]] ] +; CHECK-NEXT: [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ] +; CHECK-NEXT: [[RED:%.*]] = phi i32 [ [[BC_MERGE_RDX]], %[[SCALAR_PH]] ], [ [[RED_NEXT:%.*]], %[[LOOP]] ] ; CHECK-NEXT: [[C:%.*]] = icmp eq i32 [[START]], 0 ; CHECK-NEXT: [[IV_TRUNC:%.*]] = trunc i64 [[IV]] to i32 ; CHECK-NEXT: [[RED_NEXT]] = select i1 [[C]], i32 [[IV_TRUNC]], i32 [[RED]] ; CHECK-NEXT: [[IV_NEXT]] = add i64 [[IV]], 1 ; CHECK-NEXT: [[EC:%.*]] = icmp eq i64 [[IV]], [[N_EXT]] -; CHECK-NEXT: br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP7:![0-9]+]] +; CHECK-NEXT: br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP5:![0-9]+]] ; CHECK: [[EXIT]]: -; CHECK-NEXT: [[RED_NEXT_LCSSA:%.*]] = phi i32 [ [[RED_NEXT]], %[[LOOP]] ], [ [[RDX_SELECT]], %[[MIDDLE_BLOCK]] ], [ [[RDX_SELECT19]], %[[VEC_EPILOG_MIDDLE_BLOCK]] ] +; CHECK-NEXT: [[RED_NEXT_LCSSA:%.*]] = phi i32 [ [[RED_NEXT]], %[[LOOP]] ], [ [[RDX_SELECT19]], %[[MIDDLE_BLOCK]] ] ; CHECK-NEXT: ret i32 [[RED_NEXT_LCSSA]] ; entry: diff --git a/llvm/test/Transforms/LoopVectorize/epilog-iv-select-cmp.ll b/llvm/test/Transforms/LoopVectorize/epilog-iv-select-cmp.ll index 9c426a71fb0c9..26719f6821673 100644 --- a/llvm/test/Transforms/LoopVectorize/epilog-iv-select-cmp.ll +++ b/llvm/test/Transforms/LoopVectorize/epilog-iv-select-cmp.ll @@ -216,65 +216,21 @@ exit: define i8 @select_icmp_var_start(ptr %a, i8 %n, i8 %start) { ; CHECK-LABEL: define i8 @select_icmp_var_start( ; CHECK-SAME: ptr [[A:%.*]], i8 [[N:%.*]], i8 [[START:%.*]]) { -; CHECK-NEXT: [[ITER_CHECK:.*]]: +; CHECK-NEXT: [[ENTRY:.*]]: ; CHECK-NEXT: [[TMP0:%.*]] = add i8 [[N]], -1 ; CHECK-NEXT: [[TMP1:%.*]] = zext i8 [[TMP0]] to i32 ; CHECK-NEXT: [[TMP2:%.*]] = add nuw nsw i32 [[TMP1]], 1 -; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[TMP2]], 4 -; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label %[[VEC_EPILOG_SCALAR_PH:.*]], label %[[VECTOR_MAIN_LOOP_ITER_CHECK:.*]] -; CHECK: [[VECTOR_MAIN_LOOP_ITER_CHECK]]: ; CHECK-NEXT: [[MIN_ITERS_CHECK1:%.*]] = icmp ult i32 [[TMP2]], 4 -; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK1]], label %[[VEC_EPILOG_PH:.*]], label %[[VECTOR_PH:.*]] +; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK1]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]] ; CHECK: [[VECTOR_PH]]: -; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i32 [[TMP2]], 4 -; CHECK-NEXT: [[N_VEC:%.*]] = sub i32 [[TMP2]], [[N_MOD_VF]] -; CHECK-NEXT: [[TMP3:%.*]] = trunc i32 [[N_VEC]] to i8 -; CHECK-NEXT: br label %[[VECTOR_BODY:.*]] -; CHECK: [[VECTOR_BODY]]: -; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ] -; CHECK-NEXT: [[VEC_IND:%.*]] = phi <4 x i8> [ <i8 0, i8 1, i8 2, i8 3>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ] -; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <4 x i8> [ splat (i8 -128), %[[VECTOR_PH]] ], [ [[TMP8:%.*]], %[[VECTOR_BODY]] ] -; CHECK-NEXT: [[TMP4:%.*]] = trunc i32 [[INDEX]] to i8 -; CHECK-NEXT: [[TMP20:%.*]] = add i8 [[TMP4]], 0 -; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds i8, ptr [[A]], i8 [[TMP20]] -; CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds i8, ptr [[TMP5]], i32 0 -; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i8>, ptr [[TMP6]], align 8 -; CHECK-NEXT: [[TMP7:%.*]] = icmp eq <4 x i8> [[WIDE_LOAD]], splat (i8 3) -; CHECK-NEXT: [[TMP8]] = select <4 x i1> [[TMP7]], <4 x i8> [[VEC_IND]], <4 x i8> [[VEC_PHI]] -; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4 -; CHECK-NEXT: [[VEC_IND_NEXT]] = add <4 x i8> [[VEC_IND]], splat (i8 4) -; CHECK-NEXT: [[TMP9:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]] -; CHECK-NEXT: br i1 [[TMP9]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]] -; CHECK: [[MIDDLE_BLOCK]]: -; CHECK-NEXT: [[TMP10:%.*]] = call i8 @llvm.vector.reduce.smax.v4i8(<4 x i8> [[TMP8]]) -; CHECK-NEXT: [[RDX_SELECT_CMP:%.*]] = icmp ne i8 [[TMP10]], -128 -; CHECK-NEXT: [[RDX_SELECT:%.*]] = select i1 [[RDX_SELECT_CMP]], i8 [[TMP10]], i8 [[START]] -; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i32 [[TMP2]], [[N_VEC]] -; CHECK-NEXT: br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[VEC_EPILOG_ITER_CHECK:.*]] -; CHECK: [[VEC_EPILOG_ITER_CHECK]]: -; CHECK-NEXT: [[IND_END:%.*]] = trunc i32 [[N_VEC]] to i8 -; CHECK-NEXT: [[N_VEC_REMAINING:%.*]] = sub i32 [[TMP2]], [[N_VEC]] -; CHECK-NEXT: [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i32 [[N_VEC_REMAINING]], 4 -; CHECK-NEXT: br i1 [[MIN_EPILOG_ITERS_CHECK]], label %[[VEC_EPILOG_SCALAR_PH]], label %[[VEC_EPILOG_PH]] -; CHECK: [[VEC_EPILOG_PH]]: -; CHECK-NEXT: [[VEC_EPILOG_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], %[[VEC_EPILOG_ITER_CHECK]] ], [ 0, %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ] -; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i8 [ [[TMP3]], %[[VEC_EPILOG_ITER_CHECK]] ], [ 0, %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ] -; CHECK-NEXT: [[BC_MERGE_RDX:%.*]] = phi i8 [ [[RDX_SELECT]], %[[VEC_EPILOG_ITER_CHECK]] ], [ [[START]], %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ] -; CHECK-NEXT: [[TMP11:%.*]] = icmp eq i8 [[BC_MERGE_RDX]], [[START]] -; CHECK-NEXT: [[TMP12:%.*]] = select i1 [[TMP11]], i8 -128, i8 [[BC_MERGE_RDX]] ; CHECK-NEXT: [[N_MOD_VF2:%.*]] = urem i32 [[TMP2]], 4 ; CHECK-NEXT: [[N_VEC3:%.*]] = sub i32 [[TMP2]], [[N_MOD_VF2]] ; CHECK-NEXT: [[TMP13:%.*]] = trunc i32 [[N_VEC3]] to i8 -; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <4 x i8> poison, i8 [[BC_RESUME_VAL]], i64 0 -; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <4 x i8> [[DOTSPLATINSERT]], <4 x i8> poison, <4 x i32> zeroinitializer -; CHECK-NEXT: [[INDUCTION:%.*]] = add <4 x i8> [[DOTSPLAT]], <i8 0, i8 1, i8 2, i8 3> -; CHECK-NEXT: [[DOTSPLATINSERT8:%.*]] = insertelement <4 x i8> poison, i8 [[TMP12]], i64 0 -; CHECK-NEXT: [[DOTSPLAT9:%.*]] = shufflevector <4 x i8> [[DOTSPLATINSERT8]], <4 x i8> poison, <4 x i32> zeroinitializer -; CHECK-NEXT: br label %[[VEC_EPILOG_VECTOR_BODY:.*]] -; CHECK: [[VEC_EPILOG_VECTOR_BODY]]: -; CHECK-NEXT: [[INDEX4:%.*]] = phi i32 [ [[VEC_EPILOG_RESUME_VAL]], %[[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT11:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ] -; CHECK-NEXT: [[VEC_IND5:%.*]] = phi <4 x i8> [ [[INDUCTION]], %[[VEC_EPILOG_PH]] ], [ [[VEC_IND_NEXT6:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ] -; CHECK-NEXT: [[VEC_PHI7:%.*]] = phi <4 x i8> [ [[DOTSPLAT9]], %[[VEC_EPILOG_PH]] ], [ [[TMP17:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ] +; CHECK-NEXT: br label %[[VECTOR_BODY:.*]] +; CHECK: [[VECTOR_BODY]]: +; CHECK-NEXT: [[INDEX4:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT11:%.*]], %[[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_IND5:%.*]] = phi <4 x i8> [ <i8 0, i8 1, i8 2, i8 3>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT6:%.*]], %[[VECTOR_BODY]] ] +; CHECK-NEXT: [[VEC_PHI7:%.*]] = phi <4 x i8> [ splat (i8 -128), %[[VECTOR_PH]] ], [ [[TMP17:%.*]], %[[VECTOR_BODY]] ] ; CHECK-NEXT: [[OFFSET_IDX:%.*]] = trunc i32 [[INDEX4]] to i8 ; CHECK-NEXT: [[TMP21:%.*]] = add i8 [[OFFSET_IDX]], 0 ; CHECK-NEXT: [[TMP14:%.*]] = getelementptr inbounds i8, ptr [[A]], i8 [[TMP21]] @@ -285,29 +241,29 @@ define i8 @select_icmp_var_start(ptr %a, i8 %n, i8 %start) { ; CHECK-NEXT: [[INDEX_NEXT11]] = add nuw i32 [[INDEX4]], 4 ; CHECK-NEXT: [[VEC_IND_NEXT6]] = add <4 x i8> [[VEC_IND5]], splat (i8 4) ; CHECK-NEXT: [[TMP18:%.*]] = icmp eq i32 [[INDEX_NEXT11]], [[N_VEC3]] -; CHECK-NEXT: br i1 [[TMP18]], label %[[VEC_EPILOG_MIDDLE_BLOCK:.*]], label %[[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP9:![0-9]+]] -; CHECK: [[VEC_EPILOG_MIDDLE_BLOCK]]: +; CHECK-NEXT: br i1 [[TMP18]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]] +; CHECK: [[MIDDLE_BLOCK]]: ; CHECK-NEXT: [[TMP19:%.*]] = call i8 @llvm.vector.reduce.smax.v4i8(<4 x i8> [[TMP17]]) ; CHECK-NEXT: [[RDX_SELECT_CMP12:%.*]] = icmp ne i8 [[TMP19]], -128 ; CHECK-NEXT: [[RDX_SELECT13:%.*]] = select i1 [[RDX_SELECT_CMP12]], i8 [[TMP19]], i8 [[START]] ; CHECK-NEXT: [[CMP_N14:%.*]] = icmp eq i32 [[TMP2]], [[N_VEC3]] -; CHECK-NEXT: br i1 [[CMP_N14]], label %[[EXIT]], label %[[VEC_EPILOG_SCALAR_PH]] -; CHECK: [[VEC_EPILOG_SCALAR_PH]]: -; CHECK-NEXT: [[BC_RESUME_VAL15:%.*]] = phi i8 [ [[TMP13]], %[[VEC_EPILOG_MIDDLE_BLOCK]] ], [ 0, %[[ITER_CHECK]] ], [ [[IND_END]], %[[VEC_EPILOG_ITER_CHECK]] ] -; CHECK-NEXT: [[BC_MERGE_RDX16:%.*]] = phi i8 [ [[RDX_SELECT13]], %[[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[START]], %[[ITER_CHECK]] ], [ [[RDX_SELECT]], %[[VEC_EPILOG_ITER_CHECK]] ] +; CHECK-NEXT: br i1 [[CMP_N14]], label %[[EXIT:.*]], label %[[SCALAR_PH]] +; CHECK: [[SCALAR_PH]]: +; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i8 [ [[TMP13]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ] +; CHECK-NEXT: [[BC_MERGE_RDX:%.*]] = phi i8 [ [[RDX_SELECT13]], %[[MIDDLE_BLOCK]] ], [ [[START]], %[[ENTRY]] ] ; CHECK-NEXT: br label %[[LOOP:.*]] ; CHECK: [[LOOP]]: -; CHECK-NEXT: [[IV:%.*]] = phi i8 [ [[BC_RESUME_VAL15]], %[[VEC_EPILOG_SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ] -; CHECK-NEXT: [[RDX:%.*]] = phi i8 [ [[BC_MERGE_RDX16]], %[[VEC_EPILOG_SCALAR_PH]] ], [ [[SEL:%.*]], %[[LOOP]] ] +; CHECK-NEXT: [[IV:%.*]] = phi i8 [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ] +; CHECK-NEXT: [[RDX:%.*]] = phi i8 [ [[BC_MERGE_RDX]], %[[SCALAR_PH]] ], [ [[SEL:%.*]], %[[LOOP]] ] ; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds i8, ptr [[A]], i8 [[IV]] ; CHECK-NEXT: [[L:%.*]] = load i8, ptr [[GEP]], align 8 ; CHECK-NEXT: [[C:%.*]] = icmp eq i8 [[L]], 3 ; CHECK-NEXT: [[SEL]] = select i1 [[C]], i8 [[IV]], i8 [[RDX]] ; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i8 [[IV]], 1 ; CHECK-NEXT: [[EC:%.*]] = icmp eq i8 [[IV_NEXT]], [[N]] -; CHECK-NEXT: br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP10:![0-9]+]] +; CHECK-NEXT: br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP9:![0-9]+]] ; CHECK: [[EXIT]]: -; CHECK-NEXT: [[SEL_LCSSA:%.*]] = phi i8 [ [[SEL]], %[[LOOP]] ], [ [[RDX_SELECT]], %[[MIDDLE_BLOCK]] ], [ [[RDX_SELECT13]], %[[VEC_EPILOG_MIDDLE_BLOCK]] ] +; CHECK-NEXT: [[SEL_LCSSA:%.*]] = phi i8 [ [[SEL]], %[[LOOP]] ], [ [[RDX_SELECT13]], %[[MIDDLE_BLOCK]] ] ; CHECK-NEXT: ret i8 [[SEL_LCSSA]] ; entry: _______________________________________________ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
